Joost Vandevondele
Deputy Director For Science, Unit Head Research Infrastructure Engineering at CSCS
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolJoost Vandevondele is a scientist-turned-technology leader with 24 years of experience building and steering high-performance computing infrastructure, scientific software, and AI projects from research prototypes to production-grade platforms. As Deputy Director for Science at CSCS he co-leads strategy and >60M CHF/year financing, drives national supercomputer deployments such as "Alps," and manages multidisciplinary engineering teams and large European consortia. He blends hands-on expertise in accelerated, distributed and HPC software with academic credentials (ETH doctorate, ERC grantee) and a long record of leading community-driven codes like CP2K. Joost also played a central role in training the fully open Apertus LLM and contributes to elite open-source projects such as Stockfish, where he has optimized search and engine reliability. A member of Swiss AI advisory bodies, he uniquely spans scientific leadership, vendor engagement, and deep technical execution. Outside work he channels his computational craft into developing one of the world’s strongest AI chess programs, reflecting a persistent focus on performance, correctness, and elegant engineering.
24 years of coding experience
16 years of employment as a software developer
Master of Science in Engineering Physics (Ir.), Engineering Physics, great distinction, Master of Science in Engineering Physics (Ir.), Engineering Physics, great distinction at Ghent UniversityDoctor's Degree, Computational Chemistry, Awarded the ETH medal, Doctor's Degree, Computational Chemistry, Awarded the ETH medal at ETH ZürichMaster's degree, Master's degree at EPFL (École polytechnique fédérale de Lausanne)
English, German, Dutch, French
Github Skills (4)
cprogramming-language10
chess-engine10
c-language10
code-optimization10
Programming languages (16)
Github contributions (5)
mcostalba/Stockfish
Sep 2016 - Jul 2019
UCI chess engine
Role in this project:
Back-end Developer
Back-end DeveloperContributions:137 commits, 7 comments in 2 years 10 months
Contributions summary:Joost primarily focused on improving and optimizing the UCI chess engine. They fixed several undefined behaviors and introduced a series of code enhancements, including refactoring bonus and penalty calculations and refining parameter tweaks. The user's contributions involved tasks such as optimizing search algorithms and improving the accuracy of node searches. They also addressed potential issues in Syzygy tablebase code and enhanced the handling of the transposition table.
chess-engineuci-chess-enginemachine-learninguci
vondele/nnue-pytorch
Nov 2020 - Mar 2024
NNUE (Chess evaluation) trainer in Pytorch
Contributions:161 pushes, 135 branches, 1 comment in 3 years 4 months
pytorchevaluationtrainernnue
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.